Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 771 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1944. Min Range: -6.1944
Max Act: 6.1944. Min Act: -0.1700
Data Index: 6972020 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1944. Min Range: -6.1944
Max Act: 6.1007. Min Act: -0.1700
Data Index: 8097154 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1944. Min Range: -6.1944
Max Act: 6.0069. Min Act: -0.1700
Data Index: 6972021 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.9757. Min Act: -0.1700
Data Index: 5434519 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1944. Min Range: -6.1944
Max Act: 6.0382. Min Act: -0.1700
Data Index: 5214511 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.9757. Min Act: -0.1700
Data Index: 7384333 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.9444. Min Act: -0.1700
Data Index: 1039560 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.9444. Min Act: -0.1700
Data Index: 7662875 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.8507. Min Act: -0.1700
Data Index: 7399087 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.8194. Min Act: -0.1700
Data Index: 3595967 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7882. Min Act: -0.1700
Data Index: 580817 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7882. Min Act: -0.1700
Data Index: 2404256 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7882. Min Act: -0.1700
Data Index: 5214512 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7569. Min Act: -0.1700
Data Index: 2635577 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7257. Min Act: -0.1700
Data Index: 6371820 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.7257. Min Act: -0.1700
Data Index: 556140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.6319. Min Act: -0.1700
Data Index: 556139 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.6944. Min Act: -0.1700
Data Index: 556142 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.6944. Min Act: -0.1700
Data Index: 4698161 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1944. Min Range: -6.1944
Max Act: 5.6944. Min Act: -0.1700
Data Index: 5434520 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19